Short-Term Production Optimization Under Water-Cut Uncertainty

SPE Journal ◽  
2020 ◽  
pp. 1-21
Author(s):  
Gabriela Chaves ◽  
Danielle Monteiro ◽  
Maria Clara Duque ◽  
Virgílio Ferreira Filho ◽  
Juliana Baioco ◽  
...  
Keyword(s):  
Latin Hypercube Sampling ◽  
Stochastic Approach ◽  
Injection Rate ◽  
Production Optimization ◽  
Support Vector ◽  
Well Test ◽  
Short Term ◽  
Stochastic Solution ◽  
Water Cut ◽  
Gas Lift

Summary Short-term production optimization is an essential activity in the oil/gasfield-development process because it allows for the maximization of field production by finding the optimal operational point. In the fields that use gas lift as an artificial-lift method, the gas-lift optimization is a short-term problem. This paper presents a stochastic approach to include uncertainties from production parameters in gas-lift optimization, called the uncertain-gas-lift-optimization problem (UGLOP). Uncertainties from production variables are originated from the measurement process and the intrinsic stochastic phenomena of the production activity. The production variables usually obtained from production tests play an important role in the optimization process because they are used to update reservoir and well models. To include the uncertainties, the strategy involves representing the well-test data using nonlinear regression [support-vector regression (SVR)] and using the Latin-hypercube-sampling (LHS) method. The optimization gives a stochastic solution for the operational point. In the solved problem, this operational point is composed of the individual wells’ gas-lift-injection rate, choke opening, and well/separator routing. The value of the stochastic solution is computed to evaluate the benefit of solving the stochastic problem over the deterministic. The developed methodology is applied to wells of a Brazilian field considering uncertainty in water-cut (WC) values. As a result, an up-to-4.5% gain in oil production is observed using this approach.

Production Optimization in Mature Field Through Scenario Prediction Using a Representative Network Model: A Rapid Solution Without Well Intervention

2021 ◽  
Author(s):  
Edwin Lawrence ◽  
Marie Bjoerdal Loevereide ◽  
Sanggeetha Kalidas ◽  
Ngoc Le Le ◽  
Sarjono Tasi Antoneus ◽  
...  
Keyword(s):  
Network Model ◽  
Test Data ◽  
Production Optimization ◽  
Operating Conditions ◽  
Fine Tuning ◽  
Well Test ◽  
Production Rates ◽  
Mature Field ◽  
Gas Lift ◽  
Field Production

Abstract As part of the production optimization exercise in J field, an initiative has been taken to enhance the field production target without well intervention. J field is a mature field; the wells are mostly gas lifted, and currently it is in production decline mode. As part of this optimization exercise, a network model with multiple platforms was updated with the surface systems (separator, compressors, pumps, FPSO) and pipelines in place to understand the actual pressure drop across the system. Modelling and calibration of the well and network model was done for the entire field, and the calibrated model was used for the production optimization exercise. A representative model updated with the current operating conditions is the key for the field production and asset management. In this exercise, a multiphase flow simulator for wells and pipelines has been utilized. A total of ∼50 wells (inclusive of idle wells) has been included in the network model. Basically, the exercise started by updating the single-well model using latest well test data. During the calibration at well level, several steps were taken, such as evaluation of historical production, reservoir pressure, and well intervention. This will provide a better idea on the fine-tuning parameters. Upon completion of calibrating well models, the next level was calibration of network model at the platform level by matching against the platform operating conditions (platform production rates, separator/pipeline pressure). The last stage was performing field network model calibration to match the overall field performance. During the platform stage calibration, some parameters such as pipeline ID, horizontal flow correlation, friction factor, and holdup factor were fine-tuned to match the platform level operating conditions. Most of the wells in J field have been calibrated by meeting the success criterion, which is within +/-5% for the production rates. However, there were some challenges in matching several wells due to well test data validity especially wells located on remote platform where there is no dedicated test separator as well as the impact of gas breakthrough, which may interfere to performance of wells. These wells were decided to be retested in the following month. As for the platform level matching, five platforms were matched within +/-10% against the reported production rates. During the evaluation, it was observed there were some uncertainties in the reported water and gas rates (platform level vs. well test data). This is something that can be looked into for a better measurement in the future. By this observation, it was suggested to select Platform 1 with the most reliable test data as well as the platform rate for the optimization process and qualifying for the field trial. Nevertheless, with the representative network model, two scenarios, reducing separator pressure at platform level and gas lift optimization by an optimal gas lift rate allocation, were performed. The model predicts that a separator pressure reduction of 30 psi in Platform 1 has a potential gain of ∼300 BOPD, which is aligned with the field results. Apart from that, there was also a potential savings in gas by utilizing the predicted allocated gas lift injection rate.

Short-term steady-state production optimization of offshore oil platforms: wells with dual completion (gas-lift and ESP) and flow assurance

Top ◽  
2021 ◽  
Author(s):  
Eduardo Rauh Müller ◽  
Eduardo Camponogara ◽  
Laio Oriel Seman ◽  
Eduardo Otte Hülse ◽  
Bruno Ferreira Vieira ◽  
...  
Keyword(s):  
Steady State ◽  
Production Optimization ◽  
Flow Assurance ◽  
Short Term ◽  
Oil Platforms ◽  
Offshore Oil Platforms ◽  
State Production ◽  
Offshore Oil ◽  
Gas Lift

scholarly journals GAS LIFT OPTIMIZATION OF A MATURE WELL IN NIGER DELTA, NIGERIA USING INCOMPLETE DATASET: A CASE STUDY

2020 ◽  
Vol 4 (1) ◽  
pp. 15-18
Author(s):  
Oghenegare E. Eyankware ◽  
Idaereesoari Harriet Ateke ◽  
Okonta Nnamdi Joseph
Keyword(s):  
Niger Delta ◽  
Gas Injection ◽  
Injection Rate ◽  
Wellhead Pressure ◽  
Well Production ◽  
Artificial Lift ◽  
Lift Mechanism ◽  
Fluid Production ◽  
Water Cut ◽  
Gas Lift

Well DEF, a well located in Niger Delta region of Nigeria was shut down for 7 years. On gearing towards re-starting production, different options such as installation of gas lift mechanism, servicing and installation of packers and valves were evaluated for possibility of increasing well fluid productivity. Hence, this research was focused on optimizing well fluid productivity using PROSPER through installation of continuous gas lift mechanism on an existing well using incomplete dataset; in addition, the work evaluated effect of gas injection rates, wellhead pressure, water cut and gas gravity on efficiency of the artificial lift mechanism for improved well fluid production. Results of the study showed that optimum gas injection rate of 0.6122 MMscf/day produced well fluid production of 264.28 STB/day which is lower than pristine production rate (266 STB/day) of the well. Also, increment in wellhead pressure resulted in decrease in well production, increase in water cut facilitated reduction in well fluid productivity while gas gravity is inversely proportional to well fluid productivity. Based on results obtained, authors concluded that Well DEF does not require gaslift mechanism hence, valves and parkers need to be re-serviced and re-installed for sustained well fluid.

Digital Intelligent Artificial Lift DIAL Gas Lift Production Optimization Deployments Across Assets

2021 ◽  
Author(s):  
Ahmed Alshmakhy ◽  
Yann Bigno ◽  
Talha Saqib ◽  
Moazim Soomro ◽  
Juan Faustinelli ◽  
...  
Keyword(s):  
Injection Rate ◽  
American Petroleum Institute ◽  
Production Optimization ◽  
Flow Area ◽  
Well Production ◽  
Surface Control ◽  
Artificial Lift ◽  
Technical Details ◽  
Gas Lift

Abstract Abu Dhabi National Oil Company (ADNOC) is expanding the use of DIAL (Digital Intelligent Artificial Lift) technology, across its assets, through a range of different oil production applications. These include gas lifted single and dual completions, Extended Reach Drilling (ERD) wells and In-Situ gas lift. DIAL is a first-of-kind technology that enhances the efficiency of gas lift through downhole data, surface control and digital operations. This data driven approach enables production automation and minimizes well intervention requirements. This paper will present four different applications for the technology. These applications were selected by ADNOC assets, as they were deemed to bring the most value for DIAL implementation. The paper will describe technical details for each application, including gas lift designs, completion specificities, installation procedures and benefits observed or anticipated. A summary of the value add for each of the four applications are listed below. Gas lifted single completion is the most common application for the DIAL system. The benefits of the application have been described in previous papers and range from intervention savings to production optimization. This paper will highlight the additional benefit of automation, making full use of the system digital features. Gas lifted dual string completion, where the technology enables efficient lift of both strings, improving well production in the range of 40 to 100%. API (American Petroleum Institute) does not recommend pressure operated gas lift in dual wells. DIAL offers stability, simultaneous lifting of both strings through surface control and downhole data. ERD gas lifted well required flexibility for its gas lift operations. DIAL enables real time changes of injection depths based on reservoir response, and units can be installed deeper into the deviated section of the well without any deviation limits. In-Situ gas lift is a specific application where a gas zone is used to lift production from the oil zone in the same well. DIAL enables measurement of the gas injection rate at the point of injection, and adjustment of the flow area to optimize production. This is a world's first use of the technology for this type of application. A range of applications are described in this paper with many technical details, recommendations and lessons learnt to enable replication within the industry. Some of these applications are world first.

Using Machine Learning Algorithms on Prediction of Stock Price

2020 ◽  
Vol 12 (2) ◽  
pp. 84-99
Author(s):  
Li-Pang Chen
Keyword(s):  
Machine Learning ◽  
Stock Price ◽  
Short Term Memory ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Short Term ◽  
Learning Techniques ◽  
Historical Database ◽  
Long Short Term Memory

In this paper, we investigate analysis and prediction of the time-dependent data. We focus our attention on four different stocks are selected from Yahoo Finance historical database. To build up models and predict the future stock price, we consider three different machine learning techniques including Long Short-Term Memory (LSTM), Convolutional Neural Networks (CNN) and Support Vector Regression (SVR). By treating close price, open price, daily low, daily high, adjusted close price, and volume of trades as predictors in machine learning methods, it can be shown that the prediction accuracy is improved.

First Digital Intelligent Artificial Lift Production Optimization Technology in UAE Dual-String Gas Lift Well - Business Case and Implementation Plan

2019 ◽  
Author(s):  
Ahmed Alshmakhy ◽  
Khadija Al Daghar ◽  
Sameer Punnapala ◽  
Shamma AlShehhi ◽  
Abdel Ben Amara ◽  
...  
Keyword(s):  
Business Case ◽  
Production Optimization ◽  
Implementation Plan ◽  
Artificial Lift ◽  
Gas Lift

An application of backtracking search optimization–based least squares support vector machine for prediction of short-term wind speed

2019 ◽  
Vol 44 (3) ◽  
pp. 266-281 ◽  
Author(s):  
Zhongda Tian ◽  
Yi Ren ◽  
Gang Wang
Keyword(s):  
Support Vector Machine ◽  
Wind Speed ◽  
Prediction Model ◽  
Least Squares ◽  
Support Vector ◽  
Short Term ◽  
Backtracking Search ◽  
Wind Speed Prediction ◽  
Search Optimization ◽  
Speed Prediction

Wind speed prediction is an important technology in the wind power field; however, because of their chaotic nature, predicting wind speed accurately is difficult. Aims at this challenge, a backtracking search optimization–based least squares support vector machine model is proposed for short-term wind speed prediction. In this article, the least squares support vector machine is chosen as the short-term wind speed prediction model and backtracking search optimization algorithm is used to optimize the important parameters which influence the least squares support vector machine regression model. Furthermore, the optimal parameters of the model are obtained, and the short-term wind speed prediction model of least squares support vector machine is established through parameter optimization. For time-varying systems similar to short-term wind speed time series, a model updating method based on prediction error accuracy combined with sliding window strategy is proposed. When the prediction model does not match the actual short-term wind model, least squares support vector machine trains and re-establishes. This model updating method avoids the mismatch problem between prediction model and actual wind speed data. The actual collected short-term wind speed time series is used as the research object. Multi-step prediction simulation of short-term wind speed is carried out. The simulation results show that backtracking search optimization algorithm–based least squares support vector machine model has higher prediction accuracy and reliability for the short-term wind speed. At the same time, the prediction performance indicators are also improved. The prediction result is that root mean square error is 0.1248, mean absolute error is 0.1374, mean absolute percentile error is 0.1589% and R2 is 0.9648. When the short-term wind speed varies from 0 to 4 m/s, the average value of absolute prediction error is 0.1113 m/s, and average value of absolute relative prediction error is 8.7111%. The proposed prediction model in this article has high engineering application value.

Sign in / Sign up

Export Citation Format

Share Document